CVSL Logo
FrancaisHome
AboutPeopleResearchPublicationsEventsProfile
About
Publications

 

 

 

REPARTI

MIVIM

Progressive Human Skeleton Fitting


Jérôme Vignola, Jean-François Lalonde and Robert Bergevin


Abstract - This paper proposes a method to fit a skeleton or stick-model to a blob to determine the pose of a person in an image. The input is a binary image representing the silhouette of a person and the ouput is a stick-model coherent with the pose of the personin this image. A torso model is first defined, and is then scaled and fitted to the blob using the distance transform of the original image. Then, the fitting is performed independently for each of the four limbs (two arms, two legs), using again the distance transform. The fact that each limb is fitted independently speeds-up the fitting process, avoiding the combinatorial complexity problems that are frequent with this type of method.

download document

Bibtex:

@article{Vignola444,
    author    = { Jérôme Vignola and Jean-François Lalonde and Robert Bergevin },
    title     = { Progressive Human Skeleton Fitting },
    pages     = { 35-42 },
    year      = { 2003 },
    journal   = { Proceedings of the 16th Conference on Vision Interface }
}

Last modification: Apr 25 2003 10:59AM by vignolaj

     
   
   

©2002-. Computer Vision and Systems Laboratory. All rights reserved